ask_gpt

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses that model aliases route (e.g., bare 'gpt-5.6' goes to sol), and explains reasoning effort scale per model. However, it does not mention any potential side effects (e.g., no state changes, costs, rate limits). Still, the core behavior is well described for a read-like API call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single-paragraph description is front-loaded with the core purpose, uses bold sparingly for emphasis, and every sentence adds unique value. No redundancy; critical guidance (model selection, pattern reference) is packed efficiently. Ideal length for the information density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 5 parameters and no output schema, the description covers model selection, instructions writing, effort levels, and orchestration patterns. It could explicitly mention the return format (text) or handling of streaming, but the core completeness is high given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters, establishing a baseline of 3. The description adds significant value by mapping model choices to use cases (fast vs strong), recommending reasoning effort levels for different tasks, and explaining how to write instructions for role-specific subagents. This goes well beyond the schema's enum values and max lengths.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool asks an OpenAI model as an expert subagent, using a single interface for all models and patterns. It explicitly distinguishes from sibling tools by stating there is no separate worker vs architect tool, and refers to orchestration patterns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance: use fast models (gpt-5.6-terra, gpt-5.6-luna) with worker pattern for concrete coding, strong model (gpt-5.6-sol) with high reasoning for architecture/review. Tells agent to call list_patterns/get_pattern first for non-trivial work, giving clear when-to-use and alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.